0x2620/python-ox
2
1
Fork 0
Code Issues Pull requests Releases Wiki Activity

imdb: retun title/internationalTitle, #947; cleanup alternative titles, #963

Browse source
This commit is contained in:
j 2012-09-22 21:40:01 +02:00
parent c69a2ee825
commit da72fbdaed
2 changed files with 38 additions and 24 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
ox/text.py
View file

@ -208,7 +208,6 @@ def get_sort_name(name):
>>> get_sort_name('Scorsese, Martin') >>> get_sort_name('Scorsese, Martin')
'Scorsese, Martin' 'Scorsese, Martin'
""" """
if not ' ' in name or ', ' in name: if not ' ' in name or ', ' in name:
return name return name

61
ox/web/imdb.py
View file

@ -232,7 +232,7 @@ class Imdb(SiteParser):
're': '<span class="tv-extra">(TV series)</span>', 're': '<span class="tv-extra">(TV series)</span>',
'type': 'string' 'type': 'string'
}, },
'originalTitle': { 'title': {
'page': 'combined', 'page': 'combined',
're': '<h1>(.*?) <span>', 're': '<h1>(.*?) <span>',
'type': 'string' 'type': 'string'
@ -283,23 +283,28 @@ class Imdb(SiteParser):
time.sleep(1) time.sleep(1)
super(Imdb, self).__init__(0) super(Imdb, self).__init__(0)
#only list one country per alternative title for t in self.get('alternativeTitles', []):
for type in t[1].lower().split('/'):
def is_international_title(t): type = type.strip()
if 'script title' in t[1].lower(): return False for regexp in (
if 'recut version' in t[1].lower(): return False "^.+ \(imdb display title\) \(English title\)$",
if 'working title' in t[1].lower(): return False "^International \(English title\)$",
if 'complete title' in t[1].lower(): return False "^.+ \(English title\)$",
if 'usa (imdb display title)' in t[1].lower(): return True "^International \(.+\) \(English title\)$",
if t[1].lower() == 'usa': return True "^.+ \(.+\) \(English title\)$",
if 'international (english title)' in t[1].lower(): return True "^USA$",
#fails if orignial is english... Japan (English title) "^UK$",
#if 'english title' in t[1].lower(): return True "^USA \(.+\)$",
return False "^UK \(.+\)$",
ititle = filter(is_international_title, self.get('alternativeTitles', [])) "^International \(.+ title\)$",
if ititle: ):
self['englishTitle'] = ititle[0][0] if re.compile(regexp).findall(type):
self['title'] = self.get('englishTitle', self['originalTitle']) self['internationalTitle'] = t[0]
break
if 'internationalTitle' in self:
break
if 'internationalTitle' in self:
break
def cleanup_title(title): def cleanup_title(title):
if title.startswith('"') and title.endswith('"'): if title.startswith('"') and title.endswith('"'):
@ -307,17 +312,27 @@ class Imdb(SiteParser):
title = re.sub('\(\#[.\d]+\)', '', title) title = re.sub('\(\#[.\d]+\)', '', title)
return title.strip() return title.strip()
for t in ('title', 'englishTitle', 'originalTitle'): for t in ('title', 'internationalTitle'):
if t in self: if t in self:
self[t] = cleanup_title(self[t]) self[t] = cleanup_title(self[t])
if 'alternativeTitles' in self: if 'alternativeTitles' in self:
if len(self['alternativeTitles']) == 2 and \ if len(self['alternativeTitles']) == 2 and \
isinstance(self['alternativeTitles'][0], basestring): isinstance(self['alternativeTitles'][0], basestring):
self['alternativeTitles'] = [self['alternativeTitles']] self['alternativeTitles'] = [self['alternativeTitles']]
self['alternativeTitles'] = [[cleanup_title(t[0]), alt = {}
t[1].split(' / ')[0].split('(')[0].strip()] for t in self['alternativeTitles']:
for t in self['alternativeTitles']] title = cleanup_title(t[0])
#self[t] = re.sub('\(\#[.\d]+\)', '', self[t]) if title not in (self.get('title'), self.get('internationalTitle')):
if title not in alt:
alt[title] = []
for c in t[1].split('/'):
c = c.replace('International', '').split('(')[0].strip()
if c:
alt[title].append(c)
self['alternativeTitles'] = []
for t in sorted(alt, lambda a, b: cmp(sorted(alt[a]), sorted(alt[b]))):
if alt[t]:
self['alternativeTitles'].append((t, sorted(alt[t])))
if 'runtime' in self and self['runtime']: if 'runtime' in self and self['runtime']:
if 'min' in self['runtime']: base=60 if 'min' in self['runtime']: base=60